add proforma ion notation to the charge state rule

examples/chinese_hamster_hcd_selected_head.mzlb.txt

@@ -7,6 +7,8 @@ MS:1003188|library name=examples/chinese_hamster_hcd_selected_head
 <Spectrum=1>
 MS:1003061|library spectrum name=AAAACALTPGPLADLAAR/2_1(4,C,CAM)_46eV
 MS:1003065|spectrum aggregation type=MS:1003066|singleton spectrum
+MS:1000041|charge state=2
+MS:1000744|selected ion m/z=855.4538
 MS:1000044|dissociation method=MS:1000422|beam-type collision-induced dissociation
 [1]MS:1000045|collision energy=46
 [1]UO:0000000|unit=UO:0000266|electronvolt
@@ -20,28 +22,26 @@ MS:1000028|detector resolution=7500
 [2]UO:0000000|unit=MS:1000040|m/z
 [3]MS:1000829|isolation window upper offset=0.95
 [3]UO:0000000|unit=MS:1000040|m/z
-MS:1003085|previous MS1 scan precursor intensity=8799173.32
+MS:1003085|previous MSn-1 scan precursor intensity=8799173.32
 MS:1003086|precursor apex intensity=25273307.5
+MS:1003208|experimental precursor monoisotopic m/z=855.455
 MS:1000512|filter string="FTMS + p NSI d Full ms2 [email protected] [140.00-1725.00]"
 MS:1003059|number of peaks=87
 [4]MS:1003275|other attribute name=Se
 [4]MS:1003276|other attribute value=1(^G1:sc=8.13346e-015)
 <Analyte=1>
 MS:1000888|stripped peptide sequence=AAAACALTPGPLADLAAR
-MS:1000224|molecular mass=1710.9076
-MS:1000041|charge state=2
-MS:1000744|selected ion m/z=855.4538
-[1]MS:1001975|delta m/z=1.4
-[1]UO:0000000|unit=UO:0000169|parts per million
-MS:1003208|experimental precursor monoisotopic m/z=855.455
-MS:1003169|proforma peptidoform sequence=AAAAC[Carbamidomethyl]ALTPGPLADLAAR
+MS:1003270|proforma peptidoform ion notation=AAAAC[Carbamidomethyl]ALTPGPLADLAAR/2
 MS:1001117|theoretical mass=1708.89303961159
-[2]MS:1003048|number of enzymatic termini=2
-[2]MS:1001045|cleavage agent name=MS:1001251|Trypsin
-[2]MS:1001112|n-terminal flanking residue=R
-[2]MS:1001113|c-terminal flanking residue=L
-[2]MS:1000885|protein accession=tr|G3IJB9|G3IJB9_CRIGR UDP-N-acetylhexosamine pyrophosphorylase-like protein 1 OS=Cricetulus griseus GN=I79_023952 PE=4 SV=1
+[1]MS:1003048|number of enzymatic termini=2
+[1]MS:1001045|cleavage agent name=MS:1001251|Trypsin
+[1]MS:1001112|n-terminal flanking residue=R
+[1]MS:1001113|c-terminal flanking residue=L
+[1]MS:1000885|protein accession=tr|G3IJB9|G3IJB9_CRIGR UDP-N-acetylhexosamine pyrophosphorylase-like protein 1 OS=Cricetulus griseus GN=I79_023952 PE=4 SV=1
+MS:1003243|adduct ion mass=1710.9076
 <Interpretation=1>
+[1]MS:1001975|delta m/z=1.4
+[1]UO:0000000|unit=UO:0000169|parts per million
 MS:1003079|total unassigned intensity fraction=0.2848
 MS:1003080|top 20 peak unassigned intensity fraction=0.1879
 MS:1003289|intensity of highest unassigned peak=0.45
@@ -138,6 +138,8 @@ MS:1003290|number of unassigned peaks among top 20 peaks=4
 <Spectrum=2>
 MS:1003061|library spectrum name=AAAACALTPGPLADLAAR/2_1(4,C,CAM)_53eV
 MS:1003065|spectrum aggregation type=MS:1003066|singleton spectrum
+MS:1000041|charge state=2
+MS:1000744|selected ion m/z=855.4538
 MS:1000044|dissociation method=MS:1000422|beam-type collision-induced dissociation
 [1]MS:1000045|collision energy=53
 [1]UO:0000000|unit=UO:0000266|electronvolt
@@ -151,28 +153,26 @@ MS:1000028|detector resolution=15000
 [2]UO:0000000|unit=MS:1000040|m/z
 [3]MS:1000829|isolation window upper offset=0.95
 [3]UO:0000000|unit=MS:1000040|m/z
-MS:1003085|previous MS1 scan precursor intensity=1776618.56
+MS:1003085|previous MSn-1 scan precursor intensity=1776618.56
 MS:1003086|precursor apex intensity=12167259.65
+MS:1003208|experimental precursor monoisotopic m/z=855.4574
 MS:1000512|filter string="FTMS + p NSI d Full ms2 [email protected] [140.00-1725.00]"
 MS:1003059|number of peaks=204
 [4]MS:1003275|other attribute name=Se
 [4]MS:1003276|other attribute value=1(^G1:sc=1.31932e-020)
 <Analyte=1>
 MS:1000888|stripped peptide sequence=AAAACALTPGPLADLAAR
-MS:1000224|molecular mass=1710.9076
-MS:1000041|charge state=2
-MS:1000744|selected ion m/z=855.4538
-[1]MS:1001975|delta m/z=4.2
-[1]UO:0000000|unit=UO:0000169|parts per million
-MS:1003208|experimental precursor monoisotopic m/z=855.4574
-MS:1003169|proforma peptidoform sequence=AAAAC[Carbamidomethyl]ALTPGPLADLAAR
+MS:1003270|proforma peptidoform ion notation=AAAAC[Carbamidomethyl]ALTPGPLADLAAR/2
 MS:1001117|theoretical mass=1708.89303961159
-[2]MS:1003048|number of enzymatic termini=2
-[2]MS:1001045|cleavage agent name=MS:1001251|Trypsin
-[2]MS:1001112|n-terminal flanking residue=R
-[2]MS:1001113|c-terminal flanking residue=L
-[2]MS:1000885|protein accession=tr|G3IJB9|G3IJB9_CRIGR UDP-N-acetylhexosamine pyrophosphorylase-like protein 1 OS=Cricetulus griseus GN=I79_023952 PE=4 SV=1
+[1]MS:1003048|number of enzymatic termini=2
+[1]MS:1001045|cleavage agent name=MS:1001251|Trypsin
+[1]MS:1001112|n-terminal flanking residue=R
+[1]MS:1001113|c-terminal flanking residue=L
+[1]MS:1000885|protein accession=tr|G3IJB9|G3IJB9_CRIGR UDP-N-acetylhexosamine pyrophosphorylase-like protein 1 OS=Cricetulus griseus GN=I79_023952 PE=4 SV=1
+MS:1003243|adduct ion mass=1710.9076
 <Interpretation=1>
+[1]MS:1001975|delta m/z=4.2
+[1]UO:0000000|unit=UO:0000169|parts per million
 MS:1003079|total unassigned intensity fraction=0.3165
 MS:1003080|top 20 peak unassigned intensity fraction=0.142
 MS:1003289|intensity of highest unassigned peak=0.16
@@ -386,6 +386,8 @@ MS:1003290|number of unassigned peaks among top 20 peaks=5
 <Spectrum=3>
 MS:1003061|library spectrum name=AAAAGQTGTVPPGAPGALPLPGMAIVK/2_0_76eV
 MS:1003065|spectrum aggregation type=MS:1003066|singleton spectrum
+MS:1000041|charge state=2
+MS:1000744|selected ion m/z=1207.1672
 MS:1000044|dissociation method=MS:1000422|beam-type collision-induced dissociation
 [1]MS:1000045|collision energy=76
 [1]UO:0000000|unit=UO:0000266|electronvolt
@@ -399,28 +401,26 @@ MS:1000028|detector resolution=15000
 [2]UO:0000000|unit=MS:1000040|m/z
 [3]MS:1000829|isolation window upper offset=0.95
 [3]UO:0000000|unit=MS:1000040|m/z
-MS:1003085|previous MS1 scan precursor intensity=6939079.2
+MS:1003085|previous MSn-1 scan precursor intensity=6939079.2
 MS:1003086|precursor apex intensity=7583304.35
+MS:1003208|experimental precursor monoisotopic m/z=1207.1661
 MS:1000512|filter string="FTMS + p NSI d Full ms2 [email protected] [140.00-2000.00]"
 MS:1003059|number of peaks=122
 [4]MS:1003275|other attribute name=Se
 [4]MS:1003276|other attribute value=1(^G1:sc=1.43642e-012)
 <Analyte=1>
 MS:1000888|stripped peptide sequence=AAAAGQTGTVPPGAPGALPLPGMAIVK
-MS:1000224|molecular mass=2414.3344
-MS:1000041|charge state=2
-MS:1000744|selected ion m/z=1207.1672
-[1]MS:1001975|delta m/z=-0.9
-[1]UO:0000000|unit=UO:0000169|parts per million
-MS:1003208|experimental precursor monoisotopic m/z=1207.1661
-MS:1003169|proforma peptidoform sequence=AAAAGQTGTVPPGAPGALPLPGMAIVK
+MS:1003270|proforma peptidoform ion notation=AAAAGQTGTVPPGAPGALPLPGMAIVK/2
 MS:1001117|theoretical mass=2412.319901150229
-[2]MS:1003048|number of enzymatic termini=1
-[2]MS:1001045|cleavage agent name=MS:1001251|Trypsin
-[2]MS:1001112|n-terminal flanking residue=A
-[2]MS:1001113|c-terminal flanking residue=E
-[2]MS:1000885|protein accession=tr|G3I2Q7|G3I2Q7_CRIGR Transcription intermediary factor 1-beta OS=Cricetulus griseus GN=I79_017700 PE=4 SV=1
+[1]MS:1003048|number of enzymatic termini=1
+[1]MS:1001045|cleavage agent name=MS:1001251|Trypsin
+[1]MS:1001112|n-terminal flanking residue=A
+[1]MS:1001113|c-terminal flanking residue=E
+[1]MS:1000885|protein accession=tr|G3I2Q7|G3I2Q7_CRIGR Transcription intermediary factor 1-beta OS=Cricetulus griseus GN=I79_017700 PE=4 SV=1
+MS:1003243|adduct ion mass=2414.3344
 <Interpretation=1>
+[1]MS:1001975|delta m/z=-0.9
+[1]UO:0000000|unit=UO:0000169|parts per million
 MS:1003079|total unassigned intensity fraction=0.2591
 MS:1003080|top 20 peak unassigned intensity fraction=0.0
 MS:1003289|intensity of highest unassigned peak=0.12
@@ -552,6 +552,8 @@ MS:1003290|number of unassigned peaks among top 20 peaks=0
 <Spectrum=4>
 MS:1003061|library spectrum name=AAAAGSTSVKPIFSR/2_0_44eV
 MS:1003065|spectrum aggregation type=MS:1003066|singleton spectrum
+MS:1000041|charge state=2
+MS:1000744|selected ion m/z=731.9043
 MS:1000044|dissociation method=MS:1000422|beam-type collision-induced dissociation
 [1]MS:1000045|collision energy=44
 [1]UO:0000000|unit=UO:0000266|electronvolt
@@ -565,28 +567,26 @@ MS:1000028|detector resolution=15000
 [2]UO:0000000|unit=MS:1000040|m/z
 [3]MS:1000829|isolation window upper offset=0.95
 [3]UO:0000000|unit=MS:1000040|m/z
-MS:1003085|previous MS1 scan precursor intensity=324419.29
+MS:1003085|previous MSn-1 scan precursor intensity=324419.29
 MS:1003086|precursor apex intensity=361702.23
+MS:1003208|experimental precursor monoisotopic m/z=731.9023
 MS:1000512|filter string="FTMS + p NSI d Full ms2 [email protected] [110.00-1475.00]"
 MS:1003059|number of peaks=111
 [4]MS:1003275|other attribute name=Se
 [4]MS:1003276|other attribute value=1(^G1:sc=6.33525e-018)
 <Analyte=1>
 MS:1000888|stripped peptide sequence=AAAAGSTSVKPIFSR
-MS:1000224|molecular mass=1463.8086
-MS:1000041|charge state=2
-MS:1000744|selected ion m/z=731.9043
-[1]MS:1001975|delta m/z=-2.7
-[1]UO:0000000|unit=UO:0000169|parts per million
-MS:1003208|experimental precursor monoisotopic m/z=731.9023
-MS:1003169|proforma peptidoform sequence=AAAAGSTSVKPIFSR
+MS:1003270|proforma peptidoform ion notation=AAAAGSTSVKPIFSR/2
 MS:1001117|theoretical mass=1461.7939769138902
-[2]MS:1003048|number of enzymatic termini=1
-[2]MS:1001045|cleavage agent name=MS:1001251|Trypsin
-[2]MS:1001112|n-terminal flanking residue=Q
-[2]MS:1001113|c-terminal flanking residue=D
-[2]MS:1000885|protein accession=tr|G3I0F4|G3I0F4_CRIGR NADH dehydrogenase [ubiquinone] 1 alpha subcomplex subunit 6 OS=Cricetulus griseus GN=I79_016836 PE=4 SV=1
+[1]MS:1003048|number of enzymatic termini=1
+[1]MS:1001045|cleavage agent name=MS:1001251|Trypsin
+[1]MS:1001112|n-terminal flanking residue=Q
+[1]MS:1001113|c-terminal flanking residue=D
+[1]MS:1000885|protein accession=tr|G3I0F4|G3I0F4_CRIGR NADH dehydrogenase [ubiquinone] 1 alpha subcomplex subunit 6 OS=Cricetulus griseus GN=I79_016836 PE=4 SV=1
+MS:1003243|adduct ion mass=1463.8086
 <Interpretation=1>
+[1]MS:1001975|delta m/z=-2.7
+[1]UO:0000000|unit=UO:0000169|parts per million
 MS:1003079|total unassigned intensity fraction=0.1681
 MS:1003080|top 20 peak unassigned intensity fraction=0.0217
 MS:1003289|intensity of highest unassigned peak=0.17
@@ -707,6 +707,8 @@ MS:1003290|number of unassigned peaks among top 20 peaks=1
 <Spectrum=5>
 MS:1003061|library spectrum name=AAAAGSTSVKPIFSR/3_0_28eV
 MS:1003065|spectrum aggregation type=MS:1003066|singleton spectrum
+MS:1000041|charge state=3
+MS:1000744|selected ion m/z=488.2719
 MS:1000044|dissociation method=MS:1000422|beam-type collision-induced dissociation
 [1]MS:1000045|collision energy=28
 [1]UO:0000000|unit=UO:0000266|electronvolt
@@ -720,28 +722,26 @@ MS:1000028|detector resolution=15000
 [2]UO:0000000|unit=MS:1000040|m/z
 [3]MS:1000829|isolation window upper offset=0.95
 [3]UO:0000000|unit=MS:1000040|m/z
-MS:1003085|previous MS1 scan precursor intensity=3390555.93
+MS:1003085|previous MSn-1 scan precursor intensity=3390555.93
 MS:1003086|precursor apex intensity=3965011.86
+MS:1003208|experimental precursor monoisotopic m/z=488.2738
 MS:1000512|filter string="FTMS + p NSI d Full ms2 [email protected] [110.00-1475.00]"
 MS:1003059|number of peaks=161
 [4]MS:1003275|other attribute name=Se
 [4]MS:1003276|other attribute value=1(^G1:sc=9.67069e-018)
 <Analyte=1>
 MS:1000888|stripped peptide sequence=AAAAGSTSVKPIFSR
-MS:1000224|molecular mass=1464.8157
-MS:1000041|charge state=3
-MS:1000744|selected ion m/z=488.2719
-[1]MS:1001975|delta m/z=3.8
-[1]UO:0000000|unit=UO:0000169|parts per million
-MS:1003208|experimental precursor monoisotopic m/z=488.2738
-MS:1003169|proforma peptidoform sequence=AAAAGSTSVKPIFSR
+MS:1003270|proforma peptidoform ion notation=AAAAGSTSVKPIFSR/3
 MS:1001117|theoretical mass=1461.7939769138902
-[2]MS:1003048|number of enzymatic termini=1
-[2]MS:1001045|cleavage agent name=MS:1001251|Trypsin
-[2]MS:1001112|n-terminal flanking residue=Q
-[2]MS:1001113|c-terminal flanking residue=D
-[2]MS:1000885|protein accession=tr|G3I0F4|G3I0F4_CRIGR NADH dehydrogenase [ubiquinone] 1 alpha subcomplex subunit 6 OS=Cricetulus griseus GN=I79_016836 PE=4 SV=1
+[1]MS:1003048|number of enzymatic termini=1
+[1]MS:1001045|cleavage agent name=MS:1001251|Trypsin
+[1]MS:1001112|n-terminal flanking residue=Q
+[1]MS:1001113|c-terminal flanking residue=D
+[1]MS:1000885|protein accession=tr|G3I0F4|G3I0F4_CRIGR NADH dehydrogenase [ubiquinone] 1 alpha subcomplex subunit 6 OS=Cricetulus griseus GN=I79_016836 PE=4 SV=1
+MS:1003243|adduct ion mass=1464.8157
 <Interpretation=1>
+[1]MS:1001975|delta m/z=3.8
+[1]UO:0000000|unit=UO:0000169|parts per million
 MS:1003079|total unassigned intensity fraction=0.1804
 MS:1003080|top 20 peak unassigned intensity fraction=0.0
 MS:1003289|intensity of highest unassigned peak=0.09
@@ -912,6 +912,8 @@ MS:1003290|number of unassigned peaks among top 20 peaks=0
 <Spectrum=6>
 MS:1003061|library spectrum name=AAAALGSHGSCSSEVEK/2_1(10,C,CAM)_50eV
 MS:1003065|spectrum aggregation type=MS:1003066|singleton spectrum
+MS:1000041|charge state=2
+MS:1000744|selected ion m/z=830.8834
 MS:1000044|dissociation method=MS:1000422|beam-type collision-induced dissociation
 [1]MS:1000045|collision energy=50
 [1]UO:0000000|unit=UO:0000266|electronvolt
@@ -925,28 +927,26 @@ MS:1000028|detector resolution=15000
 [2]UO:0000000|unit=MS:1000040|m/z
 [3]MS:1000829|isolation window upper offset=0.95
 [3]UO:0000000|unit=MS:1000040|m/z
-MS:1003085|previous MS1 scan precursor intensity=30003.73
+MS:1003085|previous MSn-1 scan precursor intensity=30003.73
 MS:1003086|precursor apex intensity=28800.11
+MS:1003208|experimental precursor monoisotopic m/z=830.8868
 MS:1000512|filter string="FTMS + p NSI d Full ms2 [email protected] [110.00-1675.00]"
 MS:1003059|number of peaks=68
 [4]MS:1003275|other attribute name=Se
 [4]MS:1003276|other attribute value=1(^G1:sc=6.94218e-013)
 <Analyte=1>
 MS:1000888|stripped peptide sequence=AAAALGSHGSCSSEVEK
-MS:1000224|molecular mass=1661.7668
-MS:1000041|charge state=2
-MS:1000744|selected ion m/z=830.8834
-[1]MS:1001975|delta m/z=4.1
-[1]UO:0000000|unit=UO:0000169|parts per million
-MS:1003208|experimental precursor monoisotopic m/z=830.8868
-MS:1003169|proforma peptidoform sequence=AAAALGSHGSC[Carbamidomethyl]SSEVEK
+MS:1003270|proforma peptidoform ion notation=AAAALGSHGSC[Carbamidomethyl]SSEVEK/2
 MS:1001117|theoretical mass=1659.7522486039798
-[2]MS:1003048|number of enzymatic termini=2
-[2]MS:1001045|cleavage agent name=MS:1001251|Trypsin
-[2]MS:1001112|n-terminal flanking residue=K
-[2]MS:1001113|c-terminal flanking residue=E
-[2]MS:1000885|protein accession=tr|G3HHY9|G3HHY9_CRIGR V-type proton ATPase subunit G 1 OS=Cricetulus griseus GN=I79_010250 PE=4 SV=1
+[1]MS:1003048|number of enzymatic termini=2
+[1]MS:1001045|cleavage agent name=MS:1001251|Trypsin
+[1]MS:1001112|n-terminal flanking residue=K
+[1]MS:1001113|c-terminal flanking residue=E
+[1]MS:1000885|protein accession=tr|G3HHY9|G3HHY9_CRIGR V-type proton ATPase subunit G 1 OS=Cricetulus griseus GN=I79_010250 PE=4 SV=1
+MS:1003243|adduct ion mass=1661.7668
 <Interpretation=1>
+[1]MS:1001975|delta m/z=4.1
+[1]UO:0000000|unit=UO:0000169|parts per million
 MS:1003079|total unassigned intensity fraction=0.4368
 MS:1003080|top 20 peak unassigned intensity fraction=0.184
 MS:1003289|intensity of highest unassigned peak=0.45
@@ -1024,6 +1024,8 @@ MS:1003290|number of unassigned peaks among top 20 peaks=6
 <Spectrum=7>
 MS:1003061|library spectrum name=AAAALGSHGSCSSEVEK/2_1(10,C,CAM)_52eV
 MS:1003065|spectrum aggregation type=MS:1003066|singleton spectrum
+MS:1000041|charge state=2
+MS:1000744|selected ion m/z=830.8834
 MS:1000044|dissociation method=MS:1000422|beam-type collision-induced dissociation
 [1]MS:1000045|collision energy=52
 [1]UO:0000000|unit=UO:0000266|electronvolt
@@ -1037,28 +1039,26 @@ MS:1000028|detector resolution=15000
 [2]UO:0000000|unit=MS:1000040|m/z
 [3]MS:1000829|isolation window upper offset=0.95
 [3]UO:0000000|unit=MS:1000040|m/z
-MS:1003085|previous MS1 scan precursor intensity=9544513.13
+MS:1003085|previous MSn-1 scan precursor intensity=9544513.13
 MS:1003086|precursor apex intensity=26056925.91
+MS:1003208|experimental precursor monoisotopic m/z=830.8817
 MS:1000512|filter string="FTMS + p NSI d Full ms2 [email protected] [140.00-1675.00]"
 MS:1003059|number of peaks=402
 [4]MS:1003275|other attribute name=Se
 [4]MS:1003276|other attribute value=1(^G1:sc=6.88234e-022)
 <Analyte=1>
 MS:1000888|stripped peptide sequence=AAAALGSHGSCSSEVEK
-MS:1000224|molecular mass=1661.7668
-MS:1000041|charge state=2
-MS:1000744|selected ion m/z=830.8834
-[1]MS:1001975|delta m/z=-2.0
-[1]UO:0000000|unit=UO:0000169|parts per million
-MS:1003208|experimental precursor monoisotopic m/z=830.8817
-MS:1003169|proforma peptidoform sequence=AAAALGSHGSC[Carbamidomethyl]SSEVEK
+MS:1003270|proforma peptidoform ion notation=AAAALGSHGSC[Carbamidomethyl]SSEVEK/2
 MS:1001117|theoretical mass=1659.7522486039798
-[2]MS:1003048|number of enzymatic termini=2
-[2]MS:1001045|cleavage agent name=MS:1001251|Trypsin
-[2]MS:1001112|n-terminal flanking residue=K
-[2]MS:1001113|c-terminal flanking residue=E
-[2]MS:1000885|protein accession=tr|G3HHY9|G3HHY9_CRIGR V-type proton ATPase subunit G 1 OS=Cricetulus griseus GN=I79_010250 PE=4 SV=1
+[1]MS:1003048|number of enzymatic termini=2
+[1]MS:1001045|cleavage agent name=MS:1001251|Trypsin
+[1]MS:1001112|n-terminal flanking residue=K
+[1]MS:1001113|c-terminal flanking residue=E
+[1]MS:1000885|protein accession=tr|G3HHY9|G3HHY9_CRIGR V-type proton ATPase subunit G 1 OS=Cricetulus griseus GN=I79_010250 PE=4 SV=1
+MS:1003243|adduct ion mass=1661.7668
 <Interpretation=1>
+[1]MS:1001975|delta m/z=-2.0
+[1]UO:0000000|unit=UO:0000169|parts per million
 MS:1003079|total unassigned intensity fraction=0.339
 MS:1003080|top 20 peak unassigned intensity fraction=0.0816
 MS:1003289|intensity of highest unassigned peak=0.17

mzspeclib/validate/rules/base.json

@@ -168,6 +168,12 @@
           "allow_children": false,
           "name": "possible charge state",
           "repeatable": false
+        },
+        {
+          "accession": "MS:1003270",
+          "allow_children": false,
+          "name": "proforma peptidoform ion notation",
+          "repeatable": false
         }
       ],
       "combination_logic": "OR",